# Mercury 2 API prices

Mercury 2 (mercury) — 128k context, 50k max output.
5 metered per-token offers from 5 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Inception | $0.25 | $0.75 | $0.025 | 128k |
| NanoGPT | $0.25 | $0.75 | $0.025 | 128k |
| OpenRouter | $0.25 | $0.75 | $0.025 | 128k |
| Vercel AI Gateway | $0.25 | $0.75 | $0.025 | 128k |
| Venice AI | $0.3125 | $0.9375 | $0.0313 | 128k |

## Summary

- Cheapest input: $0.25 per 1M tokens (Inception)
- Cheapest output: $0.75 per 1M tokens (Inception)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-02-24
- Inputs: text

## FAQ

### What is the cheapest Mercury 2 API?

As of Oct 4, 2026, Inception has the lowest Mercury 2 output price at $0.75 per 1M tokens, and Inception has the lowest input price at $0.25 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Mercury 2?

5 providers list Mercury 2 on Sovyron; 5 of them sell it at a metered per-token price.

### Is Mercury 2 free?

No provider in the Sovyron catalog lists a free tier for Mercury 2.

### What is the context window of Mercury 2?

Mercury 2 supports a 128k-token context window and up to 50k output tokens.

HTML page: https://sovyron.com/models/mercury-2/
Full dataset: https://sovyron.com/data/catalog.json